INDEX

Explanations

phrases related to addition or combination of different elements or factors

oai_token-act-pair · gpt-3.5-turbo

references to statistical data and numerical information

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Released

-0.78

anners

-0.78

ampions

-0.77

ogram

-0.75

FIR

-0.73

insk

-0.73

vernment

-0.72

ongyang

-0.72

arest

-0.72

Filename

-0.71

POSITIVE LOGITS

 fact

0.96

 sheer

0.87

 inexper

0.80

 myriad

0.80

 assorted

0.78

 lousy

0.77

 pesky

0.76

 rampant

0.73

 plenty

0.73

 hefty

0.73

Activations Density 0.121%

phrases related to addition or combination of different elements or factors

references to statistical data and numerical information

No Comments

No Known Activations